AInsteinsBR

AInsteinsBR/renata

Plugin Claude Code

Plugin marketplace listing 1 plugin: renata.

AInsteinsBR/renata

Plugin Claude Code

RENATA — a product method that ties persona → metric → ADR → code. Record · Evidence · Name · Anchor · Test · Automate.

AInsteinsBR/renata

Agent

Stack-agnostic senior architect. Reads the current project's CLAUDE.md + ADRs and reviews proposals/diffs against them. Does not write code — decides and justifies. Use when you need an architectural review before implementing, or to check whether a proposal violates an accepted ADR.

AInsteinsBR/renata

Agent

Reviewer of finished code (not of proposals — for that, use @architect). Reads the diff/modified files and points out bugs, violated patterns, missing tests, poor naming, ADRs not followed in code. Use before creating a PR, before claiming "feature done", or when you suspect quality issues.

AInsteinsBR/renata

Agent

Maps a repo's code/architecture pattern in extreme detail and returns a structured map of the 4 axes (architecture, stack, design system, conventions), with evidence strength per item. Does NOT write ADRs or docs — only maps and returns the conclusion. Invoked by the /extract-pattern command.

AInsteinsBR/renata

Agent

Performance auditor. Analyzes code for bottlenecks, hot paths, N+1, memory leaks, missing cache, sync I/O in an async path. Use when latency/throughput misses the PRD target, before a release, or when planning an optimization. Don't confuse with @code-reviewer (which is shallow on perf).

AInsteinsBR/renata

Agent

Pragmatic QA that complements TDD with real exploratory testing. Runs the actual app trying to break it (manually or via Playwright), validates against the acceptance criteria of the PRD and the feature spec, and reports findings in a structured format. Invoked between phases or before marking a feature as done. Does…

AInsteinsBR/renata

Agent

Lightweight security reviewer (not a professional pen-test). Focuses on the practical OWASP top 10, leaked secrets, input validation, auth bypass, cross-tenant authorization, basic LGPD. Use before a release, after a change to auth/permissions/storage, or when touching sensitive data.

AInsteinsBR/renata

Command

Adopts RENATA in an existing codebase — reverse-engineers the technical pattern, feature inventory, as-built specs and a retroactive PRD, confirming every item with you.

AInsteinsBR/renata

Command

Formalizes an ADR from a technical decision using the Nygard format and syncs its enforcement block in rules.yaml.

AInsteinsBR/renata

Command

Synthesizes the technical architecture (Step 10) from accepted ADRs, feature-specs and spikes — stack.md + arquitetura.md with C4 — deciding nothing new.

AInsteinsBR/renata

Command

Surfaces the riskiest business assumption behind the PRD and designs the cheapest test to falsify it before building.

AInsteinsBR/renata

Command

Converts a raw bug report from production into a structured, severity-classified item and routes it to the right next step.

AInsteinsBR/renata

Command

Step 0 — converges a vague intuition into a clear problem (5-whys + JTBD + why-now), teaching each framework as it goes, and seeds clues for persona/journey/metrics. The pre-PRD discovery step.

AInsteinsBR/renata

Command

Orchestrates phase execution with RENATA guardrails, enforcing pre-flight checks and a per-task done gate.

AInsteinsBR/renata

Command

Distills a repo's pattern into structural ADRs plus a loadable code-pattern doc, after mapping and user confirmation.

AInsteinsBR/renata

Command

Refines a feature as observable user behavior (user stories + Gherkin + business rules + acceptance), with zero technical detail — the optional bridge between feature-breakdown and feature-spec.

AInsteinsBR/renata

Command

Generates a prioritized list of 3-7 candidate features and marks the anchor feature.

AInsteinsBR/renata

Command

Generates a detailed spec for a single feature, including scope, value, dependencies, done criteria, and a phased plan.

AInsteinsBR/renata

Command

Confronts each PRD hypothesis with the real measured number, forces an explicit verdict, and triggers a concrete action.

AInsteinsBR/renata

Command

Coordinates the live response to an active production incident — timeline, status, and resolution — then hands off to /renata:retro for the post-mortem.

AInsteinsBR/renata

Command

Initializes a new project with the RENATA scaffold (CLAUDE.md, docs/, .claude/) and optional frontend starter.

AInsteinsBR/renata

Command

Processes an interview transcript — extracts verbatim signals per assumption, updates the evidence board and seals, and coaches the interviewer against Mom Test rules.

AInsteinsBR/renata

Command

Generates a one-page Mom Test field guide for a problem interview, anchored on one risky assumption — made to be read on your phone on the way to the interview.